Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.5891. Min Act: -0.1700
Data Index: 584356 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.4641. Min Act: -0.1700
Data Index: 5304471 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.3078. Min Act: -0.1700
Data Index: 1742051 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.3078. Min Act: -0.1700
Data Index: 4109718 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.2766. Min Act: -0.1700
Data Index: 2029509 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.2766. Min Act: -0.1700
Data Index: 3355275 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1828. Min Act: -0.1700
Data Index: 4682135 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1828. Min Act: -0.1700
Data Index: 5007547 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1828. Min Act: -0.1700
Data Index: 7332162 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.2141. Min Act: -0.1700
Data Index: 5322052 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1516. Min Act: -0.1700
Data Index: 828438 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1516. Min Act: -0.1700
Data Index: 7585941 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1516. Min Act: -0.1700
Data Index: 3041155 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1516. Min Act: -0.1700
Data Index: 7966249 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1516. Min Act: -0.1700
Data Index: 8217808 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.1203. Min Act: -0.1700
Data Index: 155210 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.0891. Min Act: -0.1700
Data Index: 515956 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.0891. Min Act: -0.1700
Data Index: 2268360 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.0891. Min Act: -0.1700
Data Index: 1742049 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5891. Min Range: -7.5891
Max Act: 7.0578. Min Act: -0.1700
Data Index: 1219910 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19